Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1717 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.5406. Min Act: -0.1700

Data Index: 325709 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.4779. Min Act: -0.1700

Data Index: 1347534 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.4152. Min Act: -0.1700

Data Index: 164626 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3838. Min Act: -0.1700

Data Index: 696562 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3524. Min Act: -0.1700

Data Index: 929705 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3210. Min Act: -0.1700

Data Index: 167363 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3210. Min Act: -0.1700

Data Index: 743286 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.2896. Min Act: -0.1700

Data Index: 652731 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3210. Min Act: -0.1700

Data Index: 114479 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3210. Min Act: -0.1700

Data Index: 938027 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3524. Min Act: -0.1700

Data Index: 1182214 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3210. Min Act: -0.1700

Data Index: 1065996 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.2896. Min Act: -0.1700

Data Index: 1151816 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3210. Min Act: -0.1700

Data Index: 1068910 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3210. Min Act: -0.1700

Data Index: 1015040 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.2896. Min Act: -0.1700

Data Index: 872036 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3210. Min Act: -0.1700

Data Index: 284677 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.3210. Min Act: -0.1700

Data Index: 451230 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.2582. Min Act: -0.1700

Data Index: 1007479 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 3.5406. Min Range: -3.5406

Max Act: 3.2268. Min Act: -0.1700

Data Index: 191193 (C4 (Web Text))

Max Activating Token Index: 274